Neural Architectures for Named Entity Recognition
This work addresses the challenge of building effective NER systems for multiple languages without relying on extensive manual annotation or external resources, representing a significant advancement over previous methods.
The paper tackles the problem of named entity recognition (NER) by introducing two new neural architectures that eliminate the need for hand-crafted features and domain-specific knowledge, achieving state-of-the-art performance in four languages without language-specific resources.
State-of-the-art named entity recognition systems rely heavily on hand-crafted features and domain-specific knowledge in order to learn effectively from the small, supervised training corpora that are available. In this paper, we introduce two new neural architectures---one based on bidirectional LSTMs and conditional random fields, and the other that constructs and labels segments using a transition-based approach inspired by shift-reduce parsers. Our models rely on two sources of information about words: character-based word representations learned from the supervised corpus and unsupervised word representations learned from unannotated corpora. Our models obtain state-of-the-art performance in NER in four languages without resorting to any language-specific knowledge or resources such as gazetteers.